English
Related papers

Related papers: Robustness Certificates Against Adversarial Exampl…

200 papers

Adversarial attacks add perturbations to the input features with the intent of changing the classification produced by a machine learning system. Small perturbations can yield adversarial examples which are misclassified despite being…

Machine Learning · Computer Science 2019-02-05 Rakshit Agrawal , Luca de Alfaro , David Helmbold

The use of neural networks in safety-critical systems requires safe and robust models, due to the existence of adversarial attacks. Knowing the minimal adversarial perturbation of any input x, or, equivalently, knowing the distance of x…

Machine Learning · Computer Science 2022-09-12 Fabio Brau , Giulio Rossolini , Alessandro Biondi , Giorgio Buttazzo

Despite the efficacy on a variety of computer vision tasks, deep neural networks (DNNs) are vulnerable to adversarial attacks, limiting their applications in security-critical systems. Recent works have shown the possibility of generating…

Computer Vision and Pattern Recognition · Computer Science 2018-12-21 Ziang Yan , Yiwen Guo , Changshui Zhang

Neural network (NN) controllers achieve strong empirical performance on nonlinear dynamical systems, yet deploying them in safety-critical settings requires robustness to disturbances and uncertainty. We present a method for jointly…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Neelay Junnarkar , Yasin Sonmez , Murat Arcak

We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks…

Machine Learning · Computer Science 2022-02-01 Chandresh Pravin , Ivan Martino , Giuseppe Nicosia , Varun Ojha

Throughout the past five years, the susceptibility of neural networks to minimal adversarial perturbations has moved from a peculiar phenomenon to a core issue in Deep Learning. Despite much attention, however, progress towards more robust…

Machine Learning · Statistics 2019-12-13 Wieland Brendel , Jonas Rauber , Matthias Kümmerer , Ivan Ustyuzhaninov , Matthias Bethge

Recent work has shown that the training of a one-hidden-layer, scalar-output fully-connected ReLU neural network can be reformulated as a finite-dimensional convex program. Unfortunately, the scale of such a convex program grows…

Machine Learning · Computer Science 2021-05-27 Yatong Bai , Tanmay Gautam , Yu Gai , Somayeh Sojoudi

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization…

Machine Learning · Computer Science 2024-03-15 Daiwei Yu , Zhuorong Li , Lina Wei , Canghong Jin , Yun Zhang , Sixian Chan

Neural networks have received a lot of attention recently, and related security issues have come with it. Many studies have shown that neural networks are vulnerable to adversarial examples that have been artificially perturbed with…

Cryptography and Security · Computer Science 2025-08-07 Shi Pu , Fu Song , Wenjie Wang

Neural network certification methods heavily rely on convex relaxations to provide robustness guarantees. However, these relaxations are often imprecise: even the most accurate single-neuron relaxation is incomplete for general ReLU…

Machine Learning · Computer Science 2026-02-23 Yuhao Mao , Yani Zhang , Martin Vechev

Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive capabilities, they remain vulnerable to adversarial attacks, as even minor meaning-preserving changes…

Machine Learning · Computer Science 2025-12-11 Zixia Wang , Gaojie Jin , Jia Hu , Ronghui Mu

Abstracting neural networks with constraints they impose on their inputs and outputs can be very useful in the analysis of neural network classifiers and to derive optimization-based algorithms for certification of stability and robustness…

Machine Learning · Computer Science 2021-05-04 Navid Hashemi , Justin Ruths , Mahyar Fazlyab

Recent studies on the adversarial vulnerability of neural networks have shown that models trained to be more robust to adversarial attacks exhibit more interpretable saliency maps than their non-robust counterparts. We aim to quantify this…

Machine Learning · Statistics 2019-05-13 Christian Etmann , Sebastian Lunz , Peter Maass , Carola-Bibiane Schönlieb

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…

Machine Learning · Computer Science 2023-06-13 Piersilvio De Bartolomeis , Jacob Clarysse , Amartya Sanyal , Fanny Yang

In deep learning applications, robustness measures the ability of neural models that handle slight changes in input data, which could lead to potential safety hazards, especially in safety-critical applications. Pre-deployment assessment of…

Software Engineering · Computer Science 2024-04-26 Wenchuan Mu , Kwan Hui Lim

Formal verification of deep neural networks is increasingly required in safety-critical domains, yet exact reasoning over piecewise-linear (PWL) activations such as ReLU suffers from a combinatorial explosion of activation patterns. This…

Rings and Algebras · Mathematics 2026-01-01 Chandrasekhar Gokavarapu

Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…

Machine Learning · Computer Science 2018-03-26 Rajeev Ranjan , Swami Sankaranarayanan , Carlos D. Castillo , Rama Chellappa

Nearest prototype classifiers (NPCs) assign to each input point the label of the nearest prototype with respect to a chosen distance metric. A direct advantage of NPCs is that the decisions are interpretable. Previous work could provide…

Machine Learning · Computer Science 2022-07-18 Václav Voráček , Matthias Hein

To deflect adversarial attacks, a range of "certified" classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate guaranteeing that the input image is not an…

Machine Learning · Computer Science 2020-03-20 Amin Ghiasi , Ali Shafahi , Tom Goldstein

We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU). We prove that our architecture exhibits robustness to the input perturbation: the output feature of the neural…

Machine Learning · Statistics 2018-03-14 Arun Venkitaraman , Alireza M. Javid , Saikat Chatterjee
‹ Prev 1 4 5 6 7 8 10 Next ›